CN110648186A - Data analysis method, device, equipment and computer readable storage medium - Google Patents
Data analysis method, device, equipment and computer readable storage medium Download PDFInfo
- Publication number
- CN110648186A CN110648186A CN201810671639.0A CN201810671639A CN110648186A CN 110648186 A CN110648186 A CN 110648186A CN 201810671639 A CN201810671639 A CN 201810671639A CN 110648186 A CN110648186 A CN 110648186A
- Authority
- CN
- China
- Prior art keywords
- wearing
- target user
- feature information
- wearing feature
- style
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0621—Item configuration or customization
Landscapes
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Finance (AREA)
- Development Economics (AREA)
- Economics (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a data analysis method, a data analysis device, data analysis equipment and a computer readable storage medium. The method comprises the following steps: when a target user is detected, identifying first wearing feature information of the target user, and recommending commodities to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information. The current dressing style of the user is analyzed through the method, the commodities are recommended for the user according to the current dressing style of the user, the analyzing process is 'noninductive' to the user, and user experience is improved.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a data analysis method, apparatus, device, and computer-readable storage medium.
Background
The arrangement of the commodities in the store is reasonably arranged according to the popularity trend, and more popular commodities are recommended to the user, such as a main payment recommendation, so that the sale efficiency of the store can be effectively improved. However, with the continuous improvement of living and cultural levels and the continuous increase of materials, users also pursue personalization more and more, and users can select commodities according to their own conditions and preferences, which leads to that the demands of users can not be well met only according to the popularity trend of the commodities, and the sales efficiency can be better improved by combining the analysis of the personal preferences of the users.
At present, the preference of a user or the dressing style of the user is obtained mainly through communication with the user and combination of personal experience through shopping guide, or through registering customer data and performing questionnaire survey, but the method needs active cooperation of the customer, is time-consuming and labor-consuming, and is not friendly in experience.
Disclosure of Invention
In view of the above, the present application provides a data analysis method, apparatus, device and computer-readable storage medium.
Specifically, the method is realized through the following technical scheme:
in a first aspect, an embodiment of the present application provides a data analysis method, where the method includes:
when a target user is detected, identifying first wearing feature information of the target user, and recommending commodities to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information.
In a second aspect, there is provided a data analysis apparatus, comprising:
the identification unit is used for identifying first wearing feature information of a target user when the target user is detected, and recommending commodities to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information.
In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored, wherein the program, when executed by a processor, implements the steps of the method of the first aspect.
In a fourth aspect, there is provided a data analysis device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of the method of the first aspect when executing the program.
According to the embodiment of the invention, the current dressing style of the user is analyzed, the commodity is recommended for the user according to the current dressing style of the user, the analyzing process is 'insensible' for the user, and the user experience is improved. The method can also identify the commodity try-on of the user and the dressing style of the purchased commodity, and the current dressing style is obtained by combining the dressing style analysis of the historical purchase of the user and the historical try-on of the user, so that the method can be more suitable for the user, and the personal preference of the user can be better analyzed.
Drawings
Fig. 1 is a schematic view of an application scenario provided in an embodiment of the present application;
fig. 2 is a schematic flow chart of a data analysis method according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a data analysis apparatus according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a data analysis apparatus according to an embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any and all possible combinations of one or more of the associated listed items.
It is to be understood that although the terms first, second, third, etc. may be used herein to describe various information, such information should not be limited to these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present application. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.
The embodiment of the invention provides a data analysis method. The method and the system have the advantages that personal hobbies of the user can be analyzed more reasonably and more effectively, commodity recommendation is more efficient, subjective participation of the user is not needed in the whole process, and user experience is improved. The method is applicable to a data analysis system, such as a monitoring system, which includes a camera, a processor and a display. The camera is used for acquiring an image of the designated area, the processor is used for detecting a target user according to the image of the designated area, identifying or acquiring the characteristics of the target user and determining a recommended commodity according to the characteristics of the target user, and the display is used for displaying the information of the recommended commodity so as to realize interaction with the user. The following describes the data analysis system provided in the embodiment of the present invention in detail by taking a monitoring system as an example.
Fig. 1 is a schematic structural diagram of a monitoring system. As shown in fig. 1, the monitoring system includes cameras (e.g., cameras 111, 121, 122, 123, 124, 125, 126, and 131), a server 200, and terminals (e.g., a cash register terminal 310 and a terminal 320), and the cameras, the server 200, and the terminals may be connected through a wired connection or a wireless connection, such as a low-power bluetooth or Wi-Fi connection. The camera is mainly used for acquiring images of a designated area, and the designated area can be within an operation range, such as a clothing store. Specifically, the system may include a plurality of cameras, and the plurality of cameras may be respectively configured to capture images of different portions in the designated area, as shown in fig. 1, the camera 111 is installed at a position facing the entrance, and is mainly configured to capture images of the entrance, so that after the camera 111 transmits the captured images to the server 200, the server 200 may detect whether a user enters according to the images. The cameras 121, 122, 123, 124, 125 and 126 are installed on the browsing route or at both ends of the browsing route, and are mainly used for collecting images on the browsing route, so that after the cameras transmit the collected images on the browsing route to the server 200, the server 200 can track the user according to the images on the browsing route, identify and analyze the clothes that the user is standing for viewing, trying on, and the like. The camera 131 is installed right opposite to the external fitting mirror, and the camera 131 is mainly used for collecting images in front of the fitting mirror, so that after the camera 131 sends the collected images to the server 200, the server 200 can identify a user and clothes to be fitted by the user according to the images in front of the fitting mirror, and the satisfaction degree of the user on fitting the clothes can be judged by combining the length of the stay time of the user in front of the fitting mirror, the expression of the user and the like. The terminals are mainly used for data collection and information presentation (i.e. the function of the display of the aforementioned analysis system), and the system may comprise a plurality of terminals, for example, the terminal 320 and the cash register terminal 310 shown in fig. 1. The cashier terminal 310 is mainly used for acquiring information of goods purchased by the user and identity information of the user, where the identity information may include a name of the user, an ID assigned by the system to the user, and the like. The terminal 320 may be a terminal carried by the shopping guide, or may be a terminal of the customer himself, for example, the customer may log in the system using a personal mobile phone. The terminal 320 is mainly used for displaying information to customers or shopping guides, for example, displaying recommended goods for a specified customer received from the server 200. The server 200 is mainly used to implement data processing functions (i.e., functions of the processor of the analysis system), such as the operations of recognition, determination, tracking, judgment, and analysis based on the image from the camera as described above. The server 200 may further include a database, where the database may include registration information of the user, the registration information may include a user ID assigned by the system to the user, a biometric feature of the user identified from the image, information of the user purchasing a product, and the like, and the user ID, the biometric feature of the user, and the information of the user purchasing the product may be correspondingly stored in the database. Further, when the user logs in the system through the personal terminal, the terminal may be associated with the user registration information according to the user ID used when the user logs in, so that the server 200 may push recommended product information to the terminal during the user browsing process, for example, push a picture of the recommended product and a location of the recommended product. In addition, the system may also establish an account according to the registration information of the user, the user may log in the own account through the terminal, and the server 200 may send the goods to the account corresponding to the user, so that the user may obtain and view the information of the recommended goods through the personal terminal. In addition, the server 200 may also distinguish customers or service personnel (e.g., shopping guide) according to biometrics, and for the service personnel, the biometrics of the service personnel may be registered in the server 200 in advance without identifying or analyzing the characteristics of the goods related thereto (e.g., the current characteristics of the service personnel).
In addition, the monitoring system shown in fig. 1 may also include other implementations.
In one example, the cameras in the monitoring system may be panoramic cameras, which have a larger visual range, for example, for the monitoring scene shown in fig. 1, one panoramic camera may be arranged at the center of the designated area, and the panoramic camera may obtain images of all positions in the designated area.
In another example, the functions of the server 200 in the monitoring system may be integrated in the camera. For example, the panoramic camera may have a data processing function at the same time, and the function of the aforementioned server 200 is realized by the data processing function.
In another example, the functionality of the checkout terminal 310 in the monitoring system may also be implemented by the terminal 320. For example, the shopping guide may use the terminal 320 to place an order for a customer, and the terminal 320 may transmit information on an article purchased by the customer to the server 200.
In another example, the monitoring system may not include a terminal, and the server 200 places an order according to the goods taken away by the target user after detecting that the target user leaves the designated area, where the goods taken away by the target user is the goods purchased by the user this time.
It should be noted that the monitoring system shown in fig. 1 is only an example, and in a specific implementation, more or fewer components may be included according to specific needs, and a designated area may have simpler or more complex functional divisions, for example, an entrance may be set as an exit and an entrance, and the arrangement of the cameras may also include other forms.
Fig. 2 is a schematic flow chart of a data analysis method according to an embodiment of the present invention. The method may be applied to an analysis system, such as the monitoring system shown in fig. 1. As shown in fig. 2, the method specifically includes:
s210, when the target user is detected, identifying first wearing feature information of the target user, and recommending the commodity to the target user according to the first wearing feature information. Wherein the first wearing feature information is used for indicating the current dressing style of the target user. The recommended commodity is a commodity having a dressing style with a high degree of matching with the first wearing feature information.
The biological characteristics of the target user can be identified through a biological characteristic identification technology, and the biological characteristics of the target user are used as the identity characteristics of the target user, so that the aim of identifying the target user is fulfilled. The detection of the target user can be finally realized by one or more of identifying the facial features of the target user through a face identification technology, identifying the iris features of the target user through an iris identification technology, identifying the fingerprint features of the target user through a fingerprint identification technology, identifying the posture features of the target user through a posture identification technology and identifying the gait features of the target user through a gait identification technology.
The first wear characteristic information may be identified as a style confidence and may also represent statistical information for the user wearing or purchasing a corresponding style of clothing. For example, when the dressing style defined by the system includes only casual wind, business wind, and national wind, the first dressing characteristic information may be style confidence "casual wind 0.6, national wind 0.4", or statistical information "casual wind 6, national wind 4, business wind 0", or the like.
Each piece of clothes can correspond to one style and also can correspond to a plurality of styles, for example, one piece of clothes belongs to the casual wind and also belongs to the national wind, or one piece of clothes belongs to the casual wind and also belongs to the national wind, and is more inclined to the national wind. When the wearing characteristic information is determined, when the style confidence coefficient or the statistical information is determined, clothes belonging to multiple styles can be processed according to a plurality of clothes, or can be processed according to one clothes, and when the clothes are processed according to one clothes, statistics can be carried out according to the proportion of the styles, and the total number is 1.
In one example, the first wearing feature information of the target user may be determined according to a current dressing style type of the target user. The method is realized by the following steps: the target clothing corresponding to the target is detected from the image including the target user, and the method for detecting the clothing may be a target detection method. The image features, such as edges and textures, of the image of the area where the clothes are located can be extracted by using a convolutional neural network, and the image features are not described any more. Classifying the extracted styles to obtain a dressing style corresponding to the clothes, wherein the dressing style is predefined, and for example, the dressing style can include national style, gentlewoman style, business style, European style, American style, Korean style and the like. Based on this, identifying the first wearing feature information of the target user includes the steps of: inputting the collected image including the current clothing of the target user into a first convolution neural network, extracting the wearing characteristics and identifying the clothing style type of the collected image by the first convolution neural network to obtain the current clothing style type corresponding to the current clothing of the target user, and taking the current clothing style type as first clothing characteristic information.
In another example, the first wear characteristic information of the target user may be determined according to the user history information and the current dressing style type. Based on this. The method specifically comprises the following steps:
and identifying the identity characteristics of the target user, and matching the identity characteristics with the identity characteristics existing in the database. For example, the captured image may also include a facial image of the target user; after the obtaining of the current dressing style type of the target user, the method further includes: the second convolutional neural network identifies and obtains the identity characteristics of the target user according to the face image; the identity of the target user is matched against the identity already present in the database.
And if the matching is successful, acquiring second wearing feature information corresponding to the identity feature of the target user in the database. And fusing the second wearing characteristic information and the current wearing style type to obtain first wearing characteristic information.
The second wearing feature information may be style confidence, or may be represented as statistical information of clothes of a corresponding style worn or purchased by the target user.
And if the matching fails, taking the current dressing style type as the first dressing characteristic information.
Further, the information corresponding to the target user can be updated in the database. Specifically, if the matching is successful, the second wearing information stored in the database is updated to the first wearing feature information. And if the matching fails, the first wearing feature information is used as second wearing feature information, and the incidence relation between the identity feature of the target user and the second wearing feature information is stored in the database.
In addition, when the matching fails, the target user can be registered. Specifically, the corresponding relationship between the identity characteristic of the target user and the historical wearing characteristic information of the target user may be established in the database, and at this time, the historical wearing characteristic information of the target user may be set to an initial value, for example, the initial value may be 0.
It should be noted that the process of determining the user history information may be performed before or after identifying the current type of dressing style.
When recommending a commodity to a target user based on the first wearing feature information, a commodity having a high degree of matching with the first wearing feature information may be matched in the commodity database as a recommended commodity.
In this case, the product may be recommended only for the newly arrived target user or the target user at the designated location (for example, the target user in front of the terminal display screen) according to the first wearing feature information of the user. And commodities can be recommended to the target user at regular time. And recommending commodities near the position for the target user when the target user arrives at the designated position.
In one example, an image at the entrance of a specified area may be acquired, and a biometric feature of the image at the entrance of the specified area is identified, and when the biometric feature is identified, the target user is detected. Commodities in the designated area can be recommended for the target user according to the first wearing feature information of the target user.
In another example, whether a user passes through the entrance can be determined through an infrared sensor at the entrance, and when the user passes through the entrance, an image at the entrance is acquired, and a target object in the image is identified.
In another embodiment, the goods can be recommended to the user according to browsing or consumption conditions of the target user. Specifically, the method may further include the steps of:
s220, tracking the target user, and determining third wearing feature information and fourth wearing feature information of the target user. The third wearing feature information is used for indicating a dressing style corresponding to a commodity tried on by the target user, and the commodity tried on by the target user comprises a recommended commodity; the fourth wearing feature information is used for indicating a dressing style corresponding to the commodity purchased by the target user.
The third wearing characteristic may be a style confidence, a style corresponding to the tried-on clothes, and a number of times of trying on the clothes. The fourth wearing feature information may be style confidence and may also represent statistical information for the target user to purchase a corresponding style of clothing.
After the target user is identified in S210, the target user may be tracked in the designated area. For example, the target user may be tracked through images of a specified area that are continuous in time.
In the tracking of the target user within the designated area, third wearing feature information of the target user may be determined. The third wearing feature information of the target user may be used to indicate a dressing style corresponding to a commodity that the target user tries to wear, where the commodity that the target user tries to wear includes a recommended commodity. Specifically, in the tracking process, each piece of clothes tried on by the target user is identified, and the dressing style corresponding to each piece of clothes tried on is analyzed.
Further, the third wearing feature is also used for indicating the article identification of each article tried on by the target user and the fitting satisfaction of each article. Specifically, the satisfaction degree of the target user on the try-on clothes is calculated according to the stay time by calculating the stay time of the try-on clothes on the target user. The method comprises the steps of identifying the clothes information tried on by a target user according to the image information of the target user in front of a fitting mirror, analyzing and obtaining the dressing style, the clothes number and the satisfaction degree of the target user for the clothes, wherein the satisfaction degree can be measured by the stay time of the target user before the fitting mirror when the target user wears the clothes.
In addition, the popularity of the goods on sale is analyzed and evaluated according to the fitting satisfaction degree of each goods indicated by the third wearing feature information, for example, the probability of fitting clothes in a certain wearing style is high, and the popularity of clothes in the certain wearing style is high; or the probability of trying on a certain piece of clothes is low, which indicates that the popularity of the piece of clothes is low. The clothes in the designated area can be guided to be arranged according to the popularity of the clothes in the designated area.
After the target user purchases the order, third wearing characteristic information of the target user may be determined. The third wearing feature information is used for indicating a dressing style corresponding to the commodity purchased by the target user.
And S230, analyzing and obtaining fifth wearing feature information according to the first wearing feature information, the third wearing feature information and the fourth wearing feature information, wherein the fifth wearing feature information is used as a basis for recommending commodities to the target user next time.
Wherein, the fifth wearing feature information can be obtained by analyzing the first wearing feature information and the fourth wearing feature information of the target user. The fifth wearing feature information may be obtained by analyzing the first wearing feature information, the third wearing feature information, and the fourth wearing feature information. Wherein, the fifth wearing feature information is used as a basis for recommending the commodity to the target user next time. Specifically, the fifth wearing feature information may be stored in the database in correspondence with the identity feature of the target user, or the fifth wearing feature information may be replaced with the second wearing information corresponding to the identity feature of the target user in the database.
In one example, the first wearing feature information, the third wearing feature information, and the fourth wearing feature information of the target user may be weighted-averaged, respectively, to obtain fifth wearing feature information. For example, the wearing feature information may be a style confidence level, which may be a weight of each included style, for example, the first wearing feature information is "national style 0.7, gentlewoman style 0.3"; the style confidence of the first wearing information may be fused according to the third wearing feature information and the fourth wearing feature information, where the fusion may be a weighted average.
In another example, the wearing characteristics information may be tags including confidence levels of all styles, each tag corresponding to a numerical value, which may be a sum of the number of times the target user purchased and worn the style of clothing. The fifth wearing feature information may be obtained by analyzing the first wearing feature information, the third wearing feature information, and the fourth wearing feature information, and increasing the numerical value corresponding to each style label from among the first wearing feature information, the third wearing feature information, and the fourth wearing feature information.
After the fifth wearing feature information is obtained, the second wearing feature information corresponding to the identity feature of the target user in the database may be updated. When the target user detects the target user again, the first wearing feature information of the target user is determined according to the fifth wearing feature information serving as the second wearing feature information and the fifth wearing feature information of the target user at this time, and the commodity is recommended to the target user according to the first wearing feature information of the target user at this time.
In addition, for the registered user, when the target user is identified to leave, the target user does not purchase the commodity, and the wearing feature information of the target user is an initial value in the database, the related information of the target user is deleted in the database.
According to the embodiment of the invention, the current dressing style of the user is analyzed, the commodity is recommended for the user according to the current dressing style of the user, the analyzing process is 'insensible' for the user, and the user experience is improved. The method can also identify the commodity try-on of the user and the dressing style of the purchased commodity, and the current dressing style is obtained by combining the dressing style analysis of the historical purchase of the user and the historical try-on of the user, so that the method can be more suitable for the user, and the personal preference of the user can be better analyzed.
Further, when recommending commodities for the user, the current dressing style can be obtained by further combining the dressing style of the clothes worn by the user with commodities tried by the branch users and purchased commodities, so that the basis for recommending commodities is more, and the recommended commodities can be more accurate.
Corresponding to the embodiment of the data analysis method, the application also provides an embodiment of the data analysis device.
The embodiment of the data analysis device can be applied to data analysis equipment. The device embodiments may be implemented by software, or by hardware, or by a combination of hardware and software. Taking a software implementation as an example, as a device in a logical sense, a processor of the data analysis device reads corresponding computer program instructions in the nonvolatile memory into the memory for operation. From a hardware aspect, as shown in fig. 4, the present application is a hardware structure diagram of a data analysis device where a data analysis apparatus is located, except for the processor and the memory shown in fig. 4, the data analysis device where the apparatus is located in the embodiment may also include other hardware according to the actual function of the data analysis apparatus, which is not described again.
Fig. 3 is a schematic structural diagram of a data analysis apparatus according to an embodiment of the present invention. As shown in fig. 3, the apparatus includes:
the identification unit 301 is configured to identify first wearing feature information of a target user when the target user is detected, and recommend a product to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information.
In an embodiment, the identifying unit 301 is specifically configured to:
inputting a collected image including current clothes of a target user into a first convolutional neural network, extracting wearing characteristics and identifying a wearing style type of the collected image by the first convolutional neural network to obtain a current wearing style type corresponding to the clothes currently worn by the target user, and taking the current wearing style type as first wearing characteristic information.
In another embodiment, the captured image further comprises a facial image of the target user; the identification unit 301 is further configured to:
the first convolutional neural network identifies and obtains the identity characteristics of the target user according to the face image;
matching the identity characteristics of the target user with the identity characteristics existing in a database;
if the matching is successful, second wearing feature information corresponding to the identity feature of the target user is obtained in the database;
fusing the second wearing feature information and the current wearing style type to obtain the first wearing feature information;
and if the matching fails, taking the current dressing style type as the first dressing characteristic information.
In another embodiment, the apparatus further includes a storage unit 302, where the storage unit 302 is specifically configured to:
if the matching is successful, updating the second wearing information stored in the database into the first wearing feature information;
and if the matching fails, taking the first wearing feature information as the second wearing feature information, and storing the association relationship between the identity feature of the target user and the second wearing feature information in the database.
In another embodiment, the apparatus further comprises:
the tracking unit 303 is configured to track a behavior track of the target user, and determine third wearing feature information and fourth wearing feature information of the target user, where the third wearing feature information is used to indicate a dressing style corresponding to each commodity that the target user tries to wear, and the commodity that the target user tries to wear includes a recommended commodity; the fourth wearing feature information is used for indicating a dressing style corresponding to the commodity purchased by the target user;
a first analysis unit 304, configured to analyze the first wearing feature information, the third wearing feature information, and the fourth wearing feature information to obtain fifth wearing feature information;
the storage unit 302 is further configured to update the first wearing information stored in the database to the fifth wearing feature information.
In another embodiment, the third wearing feature information is further used for indicating the commodity identification of each commodity tried on by the target user and the fitting satisfaction degree of each commodity.
In another embodiment, the apparatus further comprises:
and the second analysis unit is used for analyzing and evaluating the popularity of the commodities on sale according to the fitting satisfaction degree of each commodity indicated by the third wearing feature information. The implementation process of the functions and actions of each unit in the above device is specifically described in the implementation process of the corresponding step in the above method, and is not described herein again.
For the device embodiments, since they substantially correspond to the method embodiments, reference may be made to the partial description of the method embodiments for relevant points. The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of the application. One of ordinary skill in the art can understand and implement it without inventive effort.
Fig. 4 is a schematic structural diagram of a data source server according to an embodiment of the present invention, and as shown in fig. 4, the data source server specifically includes a memory 401, a processor 402, a camera 403, and a computer program stored in the memory and capable of running on the processor. The camera 403 is configured to acquire an image of a designated area, and the processor 402 executes the program to implement the steps performed by the data source server in the embodiment shown in fig. 2.
Embodiments of the subject matter and the functional operations described in this specification can be implemented in: digital electronic circuitry, tangibly embodied computer software or firmware, computer hardware including the structures disclosed in this specification and their structural equivalents, or a combination of one or more of them. Embodiments of the subject matter described in this specification can be implemented as one or more computer programs, i.e., one or more modules of computer program instructions, encoded on a tangible, non-transitory program carrier for execution by, or to control the operation of, data processing apparatus. Alternatively or additionally, the program instructions may be encoded on an artificially generated propagated signal, e.g., a machine-generated electrical, optical, or electromagnetic signal, that is generated to encode and transmit information to suitable receiver apparatus for execution by the data processing apparatus. The computer storage medium may be a machine-readable storage device, a machine-readable storage substrate, a random or serial access memory device, or a combination of one or more of them.
The processes and logic flows described in this specification can be performed by one or more programmable computers executing one or more computer programs to perform corresponding functions by operating on input data and generating output. The processes and logic flows can also be performed by, and apparatus can also be implemented as, special purpose logic circuitry, e.g., an FPGA (field programmable gate array) or an ASIC (application-specific integrated circuit).
Computers suitable for executing computer programs include, for example, general and/or special purpose microprocessors, or any other type of central processing unit. Generally, a central processing unit will receive instructions and data from a read-only memory and/or a random access memory. The basic components of a computer include a central processing unit for implementing or executing instructions and one or more memory devices for storing instructions and data. Generally, a computer will also include, or be operatively coupled to receive data from or transfer data to, or both, one or more mass storage devices for storing data, e.g., magnetic, magneto-optical disks, or optical disks. However, a computer does not necessarily have such a device. Moreover, a computer may be embedded in another device, e.g., a mobile telephone, a Personal Digital Assistant (PDA), a mobile audio or video player, a game console, a Global Positioning System (GPS) receiver, or a portable storage device such as a Universal Serial Bus (USB) flash drive, to name a few.
Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media and memory devices, including by way of example semiconductor memory devices (e.g., EPROM, EEPROM, and flash memory devices), magnetic disks (e.g., an internal hard disk or a removable disk), magneto-optical disks, and CD ROM and DVD-ROM disks. The processor and the memory can be supplemented by, or incorporated in, special purpose logic circuitry.
While this specification contains many specific implementation details, these should not be construed as limitations on the scope of any invention or of what may be claimed, but rather as descriptions of features specific to particular embodiments of particular inventions. Certain features that are described in this specification in the context of separate embodiments can also be implemented in combination in a single embodiment. In other instances, features described in connection with one embodiment may be implemented as discrete components or in any suitable subcombination. Moreover, although features may be described above as acting in certain combinations and even initially claimed as such, one or more features from a claimed combination can in some cases be excised from the combination, and the claimed combination may be directed to a subcombination or variation of a subcombination.
Similarly, while operations are depicted in the drawings in a particular order, this should not be understood as requiring that such operations be performed in the particular order shown or in sequential order, or that all illustrated operations be performed, to achieve desirable results. In some cases, multitasking and parallel processing may be advantageous. Moreover, the separation of various system modules and components in the embodiments described above should not be understood as requiring such separation in all embodiments, and it should be understood that the described program components and systems can generally be integrated together in a single software product or packaged into multiple software products.
Thus, particular embodiments of the subject matter have been described. Other embodiments are within the scope of the following claims. In some cases, the actions recited in the claims can be performed in a different order and still achieve desirable results. Further, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some implementations, multitasking and parallel processing may be advantageous.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (12)
1. A method of data analysis, the method comprising:
when a target user is detected, identifying first wearing feature information of the target user, and recommending commodities to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information.
2. The method of claim 1, wherein the identifying first wearing feature information of the target user comprises:
inputting a collected image including current clothes of a target user into a first convolutional neural network, extracting wearing characteristics and identifying a wearing style type of the collected image by the first convolutional neural network to obtain a current wearing style type corresponding to the clothes currently worn by the target user, and taking the current wearing style type as first wearing characteristic information.
3. The method of claim 2, wherein the captured image further comprises a facial image of the target user; after the obtaining of the current dressing style type of the target user, the method further includes:
identifying and obtaining the identity characteristics of the target user by a second convolutional neural network according to the face image;
matching the identity characteristics of the target user with the identity characteristics existing in a database;
if the matching is successful, second wearing feature information corresponding to the identity feature of the target user is obtained in the database;
fusing the second wearing feature information and the current wearing style type to obtain the first wearing feature information;
and if the matching fails, taking the current dressing style type as the first dressing characteristic information.
4. The method according to claim 3, wherein after obtaining the first wearing feature information, the method further comprises:
if the matching is successful, updating the second wearing information stored in the database into the first wearing feature information;
and if the matching fails, taking the first wearing feature information as the second wearing feature information, and storing the association relationship between the identity feature of the target user and the second wearing feature information in the database.
5. The method according to claim 3 or 4, wherein after obtaining the first wearing feature information, the method further comprises:
tracking the behavior track of the target user, and determining third wearing feature information and fourth wearing feature information of the target user, wherein the third wearing feature information is used for indicating the wearing style corresponding to each commodity tried by the target user, and the commodity tried by the target user comprises recommended commodities; the fourth wearing feature information is used for indicating a dressing style corresponding to the commodity purchased by the target user;
analyzing according to the first wearing feature information, the third wearing feature information and the fourth wearing feature information to obtain fifth wearing feature information;
and updating the second wearing feature information corresponding to the identity feature of the target user stored in the database to the fifth wearing feature information.
6. A data analysis apparatus, characterized in that the apparatus comprises:
the identification unit is used for identifying first wearing feature information of a target user when the target user is detected, and recommending commodities to the target user according to the first wearing feature information; the first wearing feature information is used for indicating the current wearing style of the target user, and the recommended commodity is a commodity which has a high-matching-degree wearing style with the first wearing feature information.
7. The apparatus according to claim 6, wherein the identification unit is specifically configured to:
inputting a collected image including current clothes of a target user into a first convolutional neural network, extracting wearing characteristics and identifying a wearing style type of the collected image by the first convolutional neural network to obtain a current wearing style type corresponding to the clothes currently worn by the target user, and taking the current wearing style type as first wearing characteristic information.
8. The apparatus of claim 7, wherein the captured image further comprises a facial image of the target user; the identification unit is further configured to:
the first convolutional neural network identifies and obtains the identity characteristics of the target user according to the face image;
matching the identity characteristics of the target user with the identity characteristics existing in a database;
if the matching is successful, second wearing feature information corresponding to the identity feature of the target user is obtained in the database;
fusing the second wearing feature information and the current wearing style type to obtain the first wearing feature information;
and if the matching fails, taking the current dressing style type as the first dressing characteristic information.
9. The apparatus according to claim 8, further comprising a storage unit, the storage unit being specifically configured to:
if the matching is successful, updating the second wearing information stored in the database into the first wearing feature information;
and if the matching fails, storing the association relationship between the identity characteristic of the target user and the first wearing characteristic information in the database.
10. The apparatus of claim 8 or 9, further comprising:
the tracking unit is used for tracking the behavior track of the target user and determining third wearing feature information and fourth wearing feature information of the target user, wherein the third wearing feature information is used for indicating the wearing style corresponding to each commodity tried by the target user, and the commodity tried by the target user comprises recommended commodities; the fourth wearing feature information is used for indicating a dressing style corresponding to the commodity purchased by the target user;
the first analysis unit is used for analyzing and obtaining fifth wearing characteristic information according to the first wearing characteristic information, the third wearing characteristic information and the fourth wearing characteristic information;
the storage unit is further configured to update the first wearing information stored in the database to the fifth wearing feature information.
11. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
12. A data analysis device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1-5 are implemented when the processor executes the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810671639.0A CN110648186B (en) | 2018-06-26 | 2018-06-26 | Data analysis method, device, equipment and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810671639.0A CN110648186B (en) | 2018-06-26 | 2018-06-26 | Data analysis method, device, equipment and computer readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110648186A true CN110648186A (en) | 2020-01-03 |
| CN110648186B CN110648186B (en) | 2022-07-01 |
Family
ID=69008950
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810671639.0A Active CN110648186B (en) | 2018-06-26 | 2018-06-26 | Data analysis method, device, equipment and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110648186B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242016A (en) * | 2020-01-10 | 2020-06-05 | 深圳数联天下智能科技有限公司 | Clothes management method, control device, wardrobe and computer-readable storage medium |
| CN111445591A (en) * | 2020-03-13 | 2020-07-24 | 平安科技（深圳）有限公司 | Conference sign-in method, system, computer equipment and computer readable storage medium |
| CN112598465A (en) * | 2020-12-22 | 2021-04-02 | 浙江敦奴联合实业股份有限公司 | Ready-made garment customization method and device |
| CN112685533A (en) * | 2020-12-23 | 2021-04-20 | 京东方科技集团股份有限公司 | Salesman recommendation method and device, electronic equipment and storage medium |
| CN113469723A (en) * | 2020-04-28 | 2021-10-01 | 海信集团有限公司 | Intelligent mirror and dressing frequency statistical method |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
| CN117575636A (en) * | 2023-12-19 | 2024-02-20 | 东莞莱姆森科技建材有限公司 | Intelligent mirror control method and system based on video processing |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102402756A (en) * | 2010-09-16 | 2012-04-04 | 香港理工大学 | Intelligent clothing business system |
| EP2819002A2 (en) * | 1999-12-23 | 2014-12-31 | M.H. Segan Limited Partnership | System for viewing content over a network and method therefor |
| EP2998922A1 (en) * | 2013-05-17 | 2016-03-23 | Start Today Co., Ltd. | Wear-together-information provision system and read-information management system |
| CN107481101A (en) * | 2017-07-31 | 2017-12-15 | 广东欧珀移动通信有限公司 | Wear the clothes recommendation method and its device |
| CN107928275A (en) * | 2017-11-30 | 2018-04-20 | 深圳云天励飞技术有限公司 | Information recommendation method, intelligent mirror and storage medium |
-
2018
- 2018-06-26 CN CN201810671639.0A patent/CN110648186B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2819002A2 (en) * | 1999-12-23 | 2014-12-31 | M.H. Segan Limited Partnership | System for viewing content over a network and method therefor |
| CN102402756A (en) * | 2010-09-16 | 2012-04-04 | 香港理工大学 | Intelligent clothing business system |
| EP2998922A1 (en) * | 2013-05-17 | 2016-03-23 | Start Today Co., Ltd. | Wear-together-information provision system and read-information management system |
| CN107481101A (en) * | 2017-07-31 | 2017-12-15 | 广东欧珀移动通信有限公司 | Wear the clothes recommendation method and its device |
| CN107928275A (en) * | 2017-11-30 | 2018-04-20 | 深圳云天励飞技术有限公司 | Information recommendation method, intelligent mirror and storage medium |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111242016A (en) * | 2020-01-10 | 2020-06-05 | 深圳数联天下智能科技有限公司 | Clothes management method, control device, wardrobe and computer-readable storage medium |
| CN111445591A (en) * | 2020-03-13 | 2020-07-24 | 平安科技（深圳）有限公司 | Conference sign-in method, system, computer equipment and computer readable storage medium |
| CN113469723A (en) * | 2020-04-28 | 2021-10-01 | 海信集团有限公司 | Intelligent mirror and dressing frequency statistical method |
| CN112598465A (en) * | 2020-12-22 | 2021-04-02 | 浙江敦奴联合实业股份有限公司 | Ready-made garment customization method and device |
| CN112685533A (en) * | 2020-12-23 | 2021-04-20 | 京东方科技集团股份有限公司 | Salesman recommendation method and device, electronic equipment and storage medium |
| CN116029798A (en) * | 2023-03-22 | 2023-04-28 | 北京新发地农产品网络配送中心有限责任公司 | User demand recommendation method, system, electronic equipment and readable storage medium |
| CN117575636A (en) * | 2023-12-19 | 2024-02-20 | 东莞莱姆森科技建材有限公司 | Intelligent mirror control method and system based on video processing |
| CN117575636B (en) * | 2023-12-19 | 2024-05-24 | 东莞莱姆森科技建材有限公司 | Intelligent mirror control method and system based on video processing |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110648186B (en) | 2022-07-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110648186B (en) | Data analysis method, device, equipment and computer readable storage medium | |
| CN106776619B (en) | Method and device for determining attribute information of target object | |
| CN109993595B (en) | Method, system and equipment for personalized commodity and service recommendation | |
| US9904946B2 (en) | Reverse showrooming and merchant-customer engagement system | |
| CN109726759B (en) | Unmanned vending method, device, system, electronic equipment and computer readable medium | |
| US10410025B2 (en) | Product checkout and interest detection in retail environment using radio-frequency identification | |
| CN108051777B (en) | Target tracking method and device and electronic equipment | |
| US20110199486A1 (en) | Customer behavior recording device, customer behavior recording method, and recording medium | |
| JP2023076597A (en) | Store device, store system, store management method, and program | |
| KR101779096B1 (en) | The object pursuit way in the integration store management system of the intelligent type image analysis technology-based | |
| US20040078260A1 (en) | System for sales optimization utilizing biometric customer recognition technique | |
| JP2012208854A (en) | Action history management system and action history management method | |
| JP5002441B2 (en) | Marketing data analysis method, marketing data analysis system, data analysis server device, and program | |
| JP2004348618A (en) | Customer information collection and management method and system therefor | |
| US20230222338A1 (en) | Context-aided machine vision | |
| CN111383039A (en) | Information pushing method and device and information display system | |
| JP6517325B2 (en) | System and method for obtaining demographic information | |
| JP2013196043A (en) | Specific person monitoring system | |
| CN110766454B (en) | Method for collecting customer visit information of store and store subsystem architecture | |
| CN108961005A (en) | Information-pushing method, device, electronic equipment and medium | |
| JP2009042956A (en) | Merchandise selling device, merchandise sales management system, merchandise sales management method, and program | |
| JP7092354B2 (en) | Product information management device, product information management method and program | |
| CN104462530A (en) | Method and device for analyzing user preferences and electronic equipment | |
| JP2016143334A (en) | Purchase analysis device and purchase analysis method | |
| CN113887884A (en) | Business-super service system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |